Interested

Sure

this is brilliant @nutlope and @YoussefUiUx ! I am building something similar :-) what is the best stack to - limit sessions for built in key - prevent bots .etc

Very cool...following this 👀

Nice summary! "Coding is not the scarce skill or blocker anymore " 👆 going to change things a lot in the future

My daily drivers are Claude with opus 5..5 and @opencode with deepseek 4.1 flash

Models running on @nebiustf 😀

I have been using ds 4.1 flash +@opencode quite a bit. Works pretty well. Excited to this update

Thank you! It is a fun way to see the intelligence of the model and the speed of endpoint 😀

Race your own models 👉 sujee.github.io/llm-derby

Friday fun 🎉 The Nemotron family (Super, Lightning, Ultra) went to the carnival… and raced horses 🎪🏇 One of them is a total sprinter. Guess who? 👀 Link below 👇

now this is #usefulAI :-) great app!

We learned too much context switching takes a toll on CPUs. Turns out human brains aren't that different. 😅

thank you! yes it is one of my fav creations. Honestly started with a very simple prompt > Create visualization tracing Linux history. A 2 min video, with cool music. And tweaked it from there. i made the whole thing remixable : github.com/sujee/visual-stor…

my 'grin moment' was when I am able to make cool explainer / motion graphics videos with very simple prompts - instead of pages of storyboarding. like this one - made with Claude + opus 5.5 : youtu.be/lkOxEeqwMBo

play sujee.github.io/llm-derby/

taking muse-wonder, gpt-astra and claude-opus for a (horse) ride :-) it was a close race - latency was a big decider see below 👇 (just a fun test, not a benchmark)

this is from a benchmark we ran. (will have to check on multi turn agents)

cool, so you are doing L1 <-> L2 <-> L3 ? L1 - GPU memory L2 - CPU memory L3 - NVMe SSD / local storage